access icon free Lung vessel segmentation based on random forests

© The Institution of Engineering and Technology
Received 06/12/2016, Published 19/01/2017

Lung vessel segmentation of computed tomography (CT) images is important in clinical practise and challenging due to difficulties associated with minor size and blurred edges of lung vessels. A vessel segmentation method is proposed for lung images based on a random forest classifier and sparse auto-encoder features. First, the multi-scale representations of lung images are obtained using the Gaussian pyramid. Second, a sparse auto-encoder of three layers is trained using randomly selected patches of these images. Next, the trained weight of the sparse auto-encoder is used as the convolution kernel to extract features of different scale images. Finally, a random forest classifier is exploited to segment the vessels. The proposed method was evaluated on the original and noise-added VESSEL12 dataset that is publicly available. Comparison with some classical methods and existing machine learning methods shows that the proposed method reaches the state-of-the-art accuracy. The results also show that a shallow neural network is a powerful feature extraction tool.

Inspec keywords: neural nets; image restoration; computerised tomography; lung; medical image processing; image segmentation; feature extraction; learning (artificial intelligence); edge detection

Other keywords: sparse auto encoder; multiscale representations; noise-added VESSEL12 dataset; computed tomography; CT images; feature extraction tool; random forest classifier; sparse autoencoder features; shallow neural network; machine learning methods; Gaussian pyramid; convolution kernel; feature extraction; lung vessel segmentation; lung images; blurred edges

Subjects: Knowledge engineering techniques; Neural computing techniques; Computer vision and image processing techniques; Biology and medical computing; Optical, image and video signal processing; X-rays and particle beams (medical uses); Patient diagnostic methods and instrumentation; X-ray techniques: radiography and computed tomography (biomedical imaging/measurement)

References

    1. 1)
      • 4. Frangi, A.F., Niessen, W.J., Vincken, K.L., et al: ‘Multiscale vessel enhancement filtering’. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Cambridge MA, USA, October 1998, pp. 130–137_3, doi: 10.1007/BFb0056195.
    2. 2)
      • 7. Coates, A., Lee, H., Ng, A.: ‘An analysis of single-layer networks in unsupervised feature learning’, J. Mach. Learn. Res., 2011, 15, pp. 215–223.
    3. 3)
    4. 4)
      • 8. Ranzato, M.A., Poultney, C., Chopra, S., Cun, Y.L.: ‘Efficient learning of sparse representations with an energy-based model’. Advances in Neural Information Processing Systems, Vancouver, B.C., Canada, December 2006, pp. 1137–1144.
    5. 5)
    6. 6)
      • 6. Kiros, R., Popuri, K., Cobzas, D., et al: ‘Stacked multiscale feature learning for domain independent medical image segmentation’. Int. Workshop on Machine Learning in Medical Imaging, Boston, MA, USA, September 2014, pp. 25–32, doi: 10.1007/978-3-319-10581-9_4.
    7. 7)
    8. 8)
    9. 9)
    10. 10)
      • 10. Ginneken, B., Kerkstra, S., Shneider, C.: ‘VESSEL12 dataset’. Available at http://www.vessel12.grand-challenge.org/, accessed Fourth December 2016.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2016.4438
Loading

Related content

content/journals/10.1049/el.2016.4438
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading